{"schema":"postcutoff/event@1","as_of":"2026-10-16T12:39:00+02:00","url":"https://postcutoff.com/e/2026-10-15-flux-3-image-klein-open-weights/","md":"https://postcutoff.com/e/2026-10-15-flux-3-image-klein-open-weights/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-15-flux-3-image-klein-open-weights","date":"2026-10-15","date_precision":"day","short_title":"FLUX 3 Image Klein (5.6B open weights)","deck":null,"takeaway":"BFL's own Elo tests put it first among open-weights image models and above closed Ideogram V4.5 and FLUX.2 [pro].","category":"media-generation","category_label":"Media generation","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Black Forest Labs: FLUX 3 Image Klein (blog)","url":"https://bfl.ai/blog/flux-3-image-klein","type":"official","group":"primary","domain":"bfl.ai"},{"n":2,"title":"Hugging Face: black-forest-labs/flux-3-image-klein (model card)","url":"https://huggingface.co/black-forest-labs/flux-3-image-klein","type":"code","group":"primary","domain":"huggingface.co"},{"n":3,"title":"BFL API pricing","url":"https://docs.bfl.ai/quick_start/pricing","type":"docs","group":"primary","domain":"docs.bfl.ai"},{"n":4,"title":"GitHub: reference code","url":"https://github.com/black-forest-labs/flux-3-image-klein","type":"code","group":"primary","domain":"github.com"}],"official":4,"filed":"2026-10-16","updated":"2026-10-16","orgs":["Black Forest Labs"],"title":"Black Forest Labs releases FLUX 3 Image Klein, a 5.6B open-weights image generation and editing model","summary":"On Oct 15, 2026 Black Forest Labs released FLUX 3 Image Klein, a 5.6B-parameter open-weights model for text-to-image, image editing and multi-reference generation (up to 10 reference images) with native 4K output and bounding-box control. BFL's own Elo tests put it first among open-weights image models and above closed Ideogram V4.5 and FLUX.2 [pro]. Weights are under the FLUX Kommunity License (free commercial use under $5M annual revenue); the API price is $0.009 per 1K image.","key_facts":["Size: 5.6B image transformer (text encoder Qwen3-VL-4B-Instruct, Apache-2.0, separate); base checkpoint (50 steps, guidance 3.5) for fine-tuning and a step-distilled checkpoint (16 steps, no guidance) for low latency; FP8, INT8 and NVFP4 builds","Capabilities shared with FLUX 3 Image: native 4K generation, bounding boxes (0–1000 grid) to place, move, recolor, replace or remove elements; one model for text-to-image, single-reference editing and up to 10 reference images","BFL's internal Elo: first among open-weights models in text-to-image, multi-reference and editing; above closed Ideogram V4.5 and FLUX.2 [pro]; vs FLUX.2 [klein] 9B +91 Elo (text-to-image) and +70 (editing) with 38% fewer parameters; compared with Qwen-Image 2.1 (7B) and Krea 2 (12.9B)","Speed (BFL): API median 4.54 s (text-to-image) and 7.18 s (editing) at 1 MP incl. queueing; locally ~4 s per 1 MP on an RTX 5090 and under 9 s on an RTX 4070 (distilled, INT8, ComfyUI); under 0.6 s on a GB300 with NVFP4; INT8 build runs on 8 GB VRAM","Model card: 'Do not use the model without a prompt upsampler' (flux-3-image-klein-pup, a 9B model); peak memory on a B200 at 1024² without upsampler 31 GB (BF16) / 26 GB (FP8) / 25 GB (NVFP4)","Licence: FLUX Kommunity License v1.0: commercial output generation for users under US$5M gross annualized revenue; otherwise a commercial licence from BFL; Hugging Face access gated (contact details)","API: flux-3-image-klein on the BFL API; per-image price $0.008 (768²), $0.009 (1K), $0.011 (1.5K), $0.014 (2K), $0.036 (4K), same for generation and editing"],"key_numbers":[],"tags":["image-generation","image-editing","open-weights","flux","black-forest-labs","consumer-gpu"],"science":null,"body_md":"## What happened\n\nBlack Forest Labs (BFL) published FLUX 3 Image Klein on Oct 15, 2026 (the Hugging Face repository was created on Oct 13\nand was trending on Oct 16). It is the small, open-weights member of the FLUX 3 family announced in July. The 5.6B model\nhandles text-to-image, editing and multi-reference generation in one network and keeps two features of the larger FLUX 3\nImage: native 4K output and bounding boxes that steer where elements go (they guide placement but are not hard masks).\n\nBFL ships a base checkpoint for fine-tuning and LoRA training and a step-distilled one for fast generation, plus FP8, INT8\nand NVFP4 builds. The model card insists on a separate 9B prompt upsampler, because short prompts give generic results. The\nblog says the INT8 build runs on GPUs with 8 GB of VRAM; the card's B200 memory table (25–31 GB without the upsampler)\nmeasures a different setup, so local requirements depend on the build and the pipeline.\n\nAll quality and speed numbers are BFL's own (internal Elo evaluations; API latency measured end to end, other models timed\nfrom the client, so BFL itself says the comparison is not like for like).\n\n## Why it matters\n\nIt brings FLUX 3-class editing and 4K output to consumer GPUs a day after Krea 3 and a month after Qwen-Image 2.1, and it\nuses the same \"free under $5M revenue\" licence pattern that open image models increasingly adopt instead of Apache-2.0\n(FLUX.2 [klein] 4B was Apache-2.0).","disputed":[],"related":[{"id":"2026-10-15-krea-3-image-editing-model","url":"https://postcutoff.com/e/2026-10-15-krea-3-image-editing-model/","date":"2026-10-15","date_precision":"day","short_title":"Krea 3 image-editing model (open beta)","deck":null,"takeaway":"Image-editing models are moving from quality races to cost and latency.","category":"media-generation","category_label":"Media generation","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":3,"official":2,"filed":"2026-10-15","updated":"2026-10-15","orgs":["Krea"]},{"id":"2026-09-20-qwen-image-2-1","url":"https://postcutoff.com/e/2026-09-20-qwen-image-2-1/","date":"2026-09-20","date_precision":"day","short_title":"Alibaba releases Qwen-Image-2.1, a 7B open-weights image generation and editing model with native transparency","deck":null,"takeaway":"A 7B open model with editing, multi-reference input and native transparency makes high-quality local image generation practical on a single GPU, and it narrows the gap to the closed leaders.","category":"media-generation","category_label":"Media generation","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":5,"filed":"2026-09-30","updated":"2026-10-10","orgs":["Alibaba","Qwen"]},{"id":"2026-07-23-black-forest-labs-flux-3","url":"https://postcutoff.com/e/2026-07-23-black-forest-labs-flux-3/","date":"2026-07-23","date_precision":"day","short_title":"Black Forest Labs unveils FLUX 3","deck":"One model for images, 20-second video with audio, and robot actions","takeaway":"FLUX 3 is a concrete instance of the \"world model → robot policy\" convergence: a generative video model doubling as a robot foundation model.","category":"media-generation","category_label":"Media generation","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Black Forest Labs"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"flux-3-image-klein","name":"FLUX 3 Image Klein","url":"https://postcutoff.com/m/flux-3-image-klein/"}],"changes":[{"date":"2026-10-16","type":"filed","text":"Created (found through Hugging Face trending)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-16","run":null,"sources_read":null,"updated":"2026-10-16","human_review":null,"version":{"date":"2026-10-16"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":168,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":107,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":198,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":137,"in_training_data":false}],"short_url":null}